The Starknet-Indemnify Risk Analytics is a Django-powered microservice that provides AI-driven risk assessment for DeFi insurance underwriting. Running on port 5001, it analyzes on-chain and off-chain data to calculate insurance premiums and detect fraudulent claims.
View Swagger Docs | Risk Model Docs
- Underwriting Intelligence:
- 🧠 ML-powered risk scoring (XGBoost/Neural Nets)
- 📉 Historical claim probability analysis
- 🕵️♂️ Sybil attack detection
- Data Processing:
- On-chain behavior analysis (StarkNet L2)
- Off-chain KYC data correlation
- Real-time oracle feeds processing
- Visualization:
- Risk heatmaps for insurance pools
- Claim prediction dashboards
| Component | Technology |
|---|---|
| Framework | Django 4.2 + DRF |
| Machine Learning | PyTorch + XGBoost |
| Blockchain Data | StarkNet.py |
| Database | PostgreSQL + TimescaleDB |
| Visualization | Plotly Dash |
- Python 3.10+
- PostgreSQL 15+ with TimescaleDB
- CUDA 11.7+ (for GPU acceleration)
- Starknet full node access
- Clone the repo:
git clone https://github.com/CRYPTOInsured-Foundation/starknet-indemnify-risk-analytics.git cd starknet-indemnify-risk-analytics - Setup virtual environment:
python -m venv ven source venv/ven/bin/activate # Linux/Mac workon ven # Windows
- Install dependencies:
pip install -r requirements.txt
- Configure environment:
cp .env.example .env
- Run migrations:
python manage.py migrate
- Start the service:
python manage.py runserver 5001
- Fork the repository
- Create your feature branch:
git checkout -b feat/your-feature- Commit changes following Conventional Commits
- Push to the branch
- Open a Pull Request